Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    action followed by by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oleh
    1.59
     by
    1.40
     توسط
    1.31
    によって
    1.16
     द्वारा
    1.08
     bằng
    1.08
    由
    1.08
     দ্বারা
    1.07
    by
    1.03
     بواسطة
    1.01
    POSITIVE LOGITS
    illeri
    0.37
    eraj
    0.36
    żą
    0.36
    ็บ
    0.35
    䄪
    0.35
     বাধ্য
    0.34
    aste
    0.34
    豕
    0.34
     गायब
    0.34
     biểu
    0.33
    Act Density 0.029%

    No Known Activations